Add ProHarvest Seeds: 119 varieties + 161 cross-vendor plot reports

ProHarvest Seeds (independent Corn Belt brand, proharvestseeds.com) exposes
a public, no-auth WordPress REST API — cleaner ingestion than the HTML-only
independents. Two new sources:

- `proharvest` (variety identity, 119 row-crop varieties: 70 corn / 47 soy /
  2 wheat). Enumerated via /wp/v2/seed (seed-type taxonomy), agronomics
  parsed from each /seed/<slug>/ detail page into structured
  characteristics_groups so the ratings actually embed. Mixed scale: disease
  1-9 numeric (9=best, no flip), agronomic/general qualitative, soil HR/R.

- `proharvest_plots` (trials, data_type=trial, 161 plots, 2024+2025). Per-
  cooperator harvest reports via the custom /wp-json/proharvest/v1/plots?y=
  endpoint + PDF table extraction. Many are cross-vendor head-to-head
  (ProHarvest/Apex vs Pioneer/DEKALB/Becks/Channel/Wyffels). Handles ruled
  tables, unruled tables (text fallback; soy drops the Test-Wt column → 4 vs
  5 numerics), and off-template third-party reports (sanity-gated to verbatim
  so junk rows never ship). Image-only PDFs skipped + counted.

- rag/chunk.py: route proharvest_plots through the shared cross-vendor plot
  renderer (structured) / verbatim body (raw_text fallback).
- sources.json + lessons.md (rating-scales, trial-data).
- README/CLAUDE.md corpus inventory brought current (it had drifted: bayer
  931 not 475; ebberts/lg/agrigold were unlisted). New totals: 1,645 variety
  + 6,787 trial records.

robots.txt permissive (only search + /dealer-* disallowed); no ToS
automation clause. CI rebuilds the index from the committed corpus.
This commit is contained in:
2026-06-04 21:04:33 -04:00
parent e356633d4f
commit 89eea0f2b4
567 changed files with 80023 additions and 8 deletions
@@ -0,0 +1,45 @@
# Corn yield trial — Sam and Julie Serven (Abingdon, IL, 2025)
- **Publisher:** ProHarvest Seeds (cross-vendor plot report)
- **Crop:** Corn
- **Year:** 2025
- **Location:** Abingdon, IL · Knox County
- **Cooperator:** Sam and Julie Serven
- **Company rep:** Corey Torrance
- **Planted:** 4/24/2025
- **Harvested:** 9/12/2025
- **Previous crop:** Soybeans
- **Row width:** 30
- **Population:** 34,000 seeds/acre
- **Tillage:** Conventional
- **Irrigation:** Non-Irrigated
- **Source PDF:** https://proharvestseeds.com/wp-content/uploads/2025/10/Corn-Serven-Abingdon-IL-min.pdf
---
## Results (head-to-head)
| Rank | Brand | Hybrid/Variety | Trait | Yield/Ac | % H2O | Test Wt | +/- Ave |
|---|---|---|---|---|---|---|---|
| 1 | FS InVision | FS | 6447T RIB | 264.5 | 26.2 | None | 10.5 |
| 2 | ProHarvest | 84P78 | TRERIB | 264.32 | 26.8 | None | 10.3 |
| 3 | ProHarvest | 80P75 | PCE | 263.65 | 25.5 | None | 9.6 |
| 4 | LG Seeds | 58C16 | - | 263.61 | 25.7 | None | 9.6 |
| 5 | LG Seeds | LG64C43 | VT2PRO | 262.52 | 27.3 | None | 8.5 |
| 6 | ProHarvest | 78P95 | PCE | 261.42 | 24.4 | None | 7.4 |
| 7 | FS InVision | FS | 6349PC RA | 257.65 | 25.1 | None | 3.6 |
| 7 | LG Seeds | LG65C30 | VT2P | 257.65 | 28.2 | None | 3.6 |
| 8 | Wyffels | 7424 | - | 256.93 | 27.4 | None | 2.9 |
| 9 | ProHarvest | 86P55 | TRERIB | 256.41 | 26.8 | None | 2.4 |
| 10 | ProHarvest | 80P75 | PCE | 255.29 | 25 | None | 1.3 |
| 11 | ProHarvest | 83P66 | VT2PRIB | 254.87 | 26.1 | None | 0.8 |
| 12 | ProHarvest | 81P45 | TRERIB | 251.85 | 26.01 | None | -2.2 |
| 13 | LG Seeds | 60C84 | - | 251.02 | 24.66 | None | -3 |
| 14 | ProHarvest | 80P75 | PCE | 249.65 | 24.97 | None | -4.4 |
| 15 | Wyffels | 7485 | - | 248.89 | 25.4 | None | -5.1 |
| 16 | FS InVision | FS | 6545V RIB | 248.03 | 23.7 | None | -6 |
| 17 | LG Seeds | LG62C73 | VT2PRIB | 246.87 | 25.3 | None | -7.2 |
| 18 | LG Seeds | LG63C82 | DGVT2P RIB | 246.86 | 26.7 | None | -7.2 |
| 19 | LG Seeds | 63C32 | - | 245.54 | 25.5 | None | -8.5 |
| 20 | ProHarvest | 85P58 | VT2PRIB | 243.84 | 23.4 | None | -10.2 |
| 21 | Wyffels | W6505RIB | - | 237.21 | 23.2 | None | -16.8 |